Polar Sine Based Siamese Neural Network for Gesture Recognition

Samuel Berlemont (1, 2) , Grégoire Lefebvre (2) , Stefan Duffner (1) , Christophe Garcia (1)

1 imagine - Extraction de Caractéristiques et Identification
2 Orange Labs [Meylan]

Our work focuses on metric learning between gesture sample signatures using Siamese Neural Networks (SNN), which aims at model-ing semantic relations between classes to extract discriminative features. Our contribution is the notion of polar sine which enables a redefini-tion of the angular problem. Our final proposal improves inertial gesture classification in two challenging test scenarios, with respective average classification rates of 0.934 ± 0.011 and 0.776 ± 0.025.

Mots clés: Siamese Neural Network; Metric Learning; Polar Sine; Gesture Recognition

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Réseau de neurones [cs.NE]; Robotique [cs.RO]

Samuel Berlemont, Grégoire Lefebvre, Stefan Duffner, Christophe Garcia. Polar Sine Based Siamese Neural Network for Gesture Recognition. International Conference on Artificial Neural Networks, Sep 2016, Barcelona, Spain. ⟨10.1007/978-3-319-44781-0_48⟩. ⟨hal-01369302⟩